Upload Date | May 18 2025 02:58 AM |
Views | 4 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Qualcomm ARMv8 |
System Information | |
---|---|
Operating System | Android 15 |
Model | samsung SM-S931B |
Model ID | samsung SM-S931B |
Motherboard | sun |
Governor | walt |
CPU Information | |
---|---|
Name | Qualcomm ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 81 architecture 8 variant 3 part 1 revision 4 |
Base Frequency | 3.53 GHz |
Cluster 1 | 6 Cores @ 3.53 GHz |
Cluster 2 | 2 Cores @ 4.47 GHz |
Memory Information | |
---|---|
Size | 10.86 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1483
275.7 IPS |
|
Image Classification (HP)
|
100% |
1989
369.9 IPS |
|
Image Classification (Q)
|
100% |
4498
836.6 IPS |
|
Image Segmentation (SP)
|
100% |
2529
41.0 IPS |
|
Image Segmentation (HP)
|
100% |
2520
40.9 IPS |
|
Image Segmentation (Q)
|
98% |
5339
86.8 IPS |
|
Pose Estimation (SP)
|
100% |
5853
6.83 IPS |
|
Pose Estimation (HP)
|
100% |
5594
6.53 IPS |
|
Pose Estimation (Q)
|
84% |
14125
16.8 IPS |
|
Object Detection (SP)
|
98% |
1767
140.6 IPS |
|
Object Detection (HP)
|
98% |
1823
145.0 IPS |
|
Object Detection (Q)
|
83% |
4118
332.7 IPS |
|
Face Detection (SP)
|
100% |
4640
55.1 IPS |
|
Face Detection (HP)
|
100% |
4609
54.8 IPS |
|
Face Detection (Q)
|
95% |
9943
118.7 IPS |
|
Depth Estimation (SP)
|
99% |
4865
37.6 IPS |
|
Depth Estimation (HP)
|
99% |
4742
36.6 IPS |
|
Depth Estimation (Q)
|
64% |
11062
101.3 IPS |
|
Style Transfer (SP)
|
89% |
12008
15.6 IPS |
|
Style Transfer (HP)
|
89% |
11903
15.5 IPS |
|
Style Transfer (Q)
|
98% |
25105
32.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
2502
92.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
2486
91.8 IPS |
|
Image Super-Resolution (Q)
|
97% |
6781
251.3 IPS |
|
Text Classification (SP)
|
100% |
996
1.33 KIPS |
|
Text Classification (HP)
|
99% |
968
1.29 KIPS |
|
Text Classification (Q)
|
88% |
1045
1.41 KIPS |
|
Machine Translation (SP)
|
100% |
1426
24.6 IPS |
|
Machine Translation (HP)
|
100% |
1409
24.3 IPS |
|
Machine Translation (Q)
|
50% |
569
20.2 IPS |